Motivated learning for the development of autonomous systems
A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine’s behavior based on competition between dynami...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/96713 http://hdl.handle.net/10220/13056 |
| _version_ | 1811688743960051712 |
|---|---|
| author | Starzyk, Janusz A. Graham, James T. Raif, Pawel Tan, Ah-Hwee |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Starzyk, Janusz A. Graham, James T. Raif, Pawel Tan, Ah-Hwee |
| author_sort | Starzyk, Janusz A. |
| collection | NTU |
| description | A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine
to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine’s behavior
based on competition between dynamically-changing pain signals. This provides an interplay of externally driven and internally
generated control signals. It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values
than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in
dynamically-changing environments. In addition, this paper shows the basic neural network structures used to create abstract motivations,
higher level goals, and subgoals. Finally, simulation results show comparisons between ML and RL in environments of gradually
increasing sophistication and levels of difficulty. |
| first_indexed | 2024-10-01T05:37:04Z |
| format | Journal Article |
| id | ntu-10356/96713 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:37:04Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/967132020-05-28T07:18:14Z Motivated learning for the development of autonomous systems Starzyk, Janusz A. Graham, James T. Raif, Pawel Tan, Ah-Hwee School of Computer Engineering DRNTU::Engineering::Computer science and engineering A new machine learning approach known as motivated learning (ML) is presented in this work. Motivated learning drives a machine to develop abstract motivations and choose its own goals. ML also provides a self-organizing system that controls a machine’s behavior based on competition between dynamically-changing pain signals. This provides an interplay of externally driven and internally generated control signals. It is demonstrated that ML not only yields a more sophisticated learning mechanism and system of values than reinforcement learning (RL), but is also more efficient in learning complex relations and delivers better performance than RL in dynamically-changing environments. In addition, this paper shows the basic neural network structures used to create abstract motivations, higher level goals, and subgoals. Finally, simulation results show comparisons between ML and RL in environments of gradually increasing sophistication and levels of difficulty. 2013-08-06T06:03:37Z 2019-12-06T19:34:11Z 2013-08-06T06:03:37Z 2019-12-06T19:34:11Z 2011 2011 Journal Article Starzyk, J. A., Graham, J. T., Raif, P.,& Tan, A. H. (2012). Motivated learning for the development of autonomous systems. Cognitive Systems Research, 14(1), 10-25. 1389-0417 https://hdl.handle.net/10356/96713 http://hdl.handle.net/10220/13056 10.1016/j.cogsys.2010.12.009 en Cognitive systems research |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Starzyk, Janusz A. Graham, James T. Raif, Pawel Tan, Ah-Hwee Motivated learning for the development of autonomous systems |
| title | Motivated learning for the development of autonomous systems |
| title_full | Motivated learning for the development of autonomous systems |
| title_fullStr | Motivated learning for the development of autonomous systems |
| title_full_unstemmed | Motivated learning for the development of autonomous systems |
| title_short | Motivated learning for the development of autonomous systems |
| title_sort | motivated learning for the development of autonomous systems |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/96713 http://hdl.handle.net/10220/13056 |
| work_keys_str_mv | AT starzykjanusza motivatedlearningforthedevelopmentofautonomoussystems AT grahamjamest motivatedlearningforthedevelopmentofautonomoussystems AT raifpawel motivatedlearningforthedevelopmentofautonomoussystems AT tanahhwee motivatedlearningforthedevelopmentofautonomoussystems |